Object tracker for visually tracking object motion

Details Object tracker for visually tracking object motion Object tracker for visually tracking object motion

2011-05-10

2011-05-10

Tabatabai, Abolfazl (Department: 2624)

Image analysis

Applications

Target tracking or detecting

C348S154000, C348S155000, C348S169000

Reexamination Certificate

active

07940957

ABSTRACT:
A tracking start-and-stop determining unit of a tracking processing unit determines whether to start or stop tracking based on a predetermined condition. During tracking, a sampling unit29creates or eliminates particles using a probability density distribution estimated for the previous image frame. A first to nthmodel tracking units transit the particles according to motion models respectively assigned, and observe the likelihood of a candidate curve corresponding to each particle with respect to an edge image generated by an image processing unit. A tracking integration unit determines a motion model which causes the highest likelihood, and estimates a probability density distribution using an observation likelihood based on the motion model.

REFERENCES:
patent: 7376246 (2008-05-01), Shao et al.
patent: 7835542 (2010-11-01), Lin et al.
patent: 7860344 (2010-12-01), Fitzpatrick et al.
patent: 2001-92978 (2001-04-01), None
patent: 2005-165688 (2005-06-01), None
Michael Isard et al. “Contour Tracking by stochastic propagation of conditional density” Proc. European Conference on Computer Vision, vol. 1, pp. 343-356, 1996.
Michael Isard et al. “A mixed-state CONDENSATION tracker with automatic model-switching” Proc. 6th Int. Conf. Computer Vision, 1998.
Michael Isard et al. “ICONDENSATION: Unifying low-level and high-level tracking in a stochastic framework” Proc 5th European Conf. Computer Vision, 1998.
Michael Isard et al. “CONDENSATION—conditional density propagation for visual tracking” Int. J. Computer Vision, 1998.
Notification of Reason(s) for Refusal dated Jul. 1, 2008, from the corresponding Japanese Application.
Jianyu Wang, et al. “Interacting Multiple Model Particle Filter to Adaptive Visual Tracking” Proceedings of the Third International Conference on Image and Graphics, IEEE Computer Society, Dec. 31, 2004, pp. 568-571.
Kenji Oka et al. “Head Pose Estimation System Based on Particle Filtering with Adaptive Diffusion Control”, IEICE Report, vol. J88-D-II, No. 8, Aug. 1, 2005, pp. 1601-1613.

Affiliated with

Also associated with

Rating

Object tracker for visually tracking object motion does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Object tracker for visually tracking object motion, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Object tracker for visually tracking object motion will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2680330